home / mcp / airtable mcp server
This read-only MCP Server allows you to connect to Airtable data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).
Configuration
View docs{
"mcpServers": {
"cdatasoftware-airtable-mcp-server-by-cdata": {
"command": "java",
"args": [
"-jar",
"/PATH/TO/CDataMCP-jar-with-dependencies.jar",
"/PATH/TO/airtable.prp"
]
}
}
}You can run a local, read-only MCP server that exposes live Airtable data through a simple MCP interface. This lets AI clients ask natural-language questions and retrieve up-to-date Airtable information without writing SQL.
Your MCP server provides a set of built-in tools that let an AI client query Airtable data as if it were relational tables. After you start the server, you interact with it through an MCP client on the same machine. You can ask questions like which opportunities are open or which records exist in a given table, and the AI client will retrieve results from Airtable in real time. To use it effectively, run the MCP server with your Airtable configuration, then connect your MCP client to the local stdio server. The client will automatically discover the available tables and columns and use the built-in tools to run queries or fetch metadata.
# prerequisites
- Java Runtime Environment (JRE) or JDK
- Maven (for building the MCP server from source)
- Airtable data access via CData JDBC Driver (download and license steps below)
# 1) Build the MCP server from source
git clone https://github.com/cdatasoftware/airtable-mcp-server-by-cdata.git
cd airtable-mcp-server-by-cdata
mvn clean install
# This creates the JAR file: CDataMCP-jar-with-dependencies.jar
# 2) Download and install the CData JDBC Driver for Airtable
# Visit: https://www.cdata.com/drivers/airtable/download/jdbc
# 3) License the CData JDBC Driver
# Locate the Driver in your installation, then run the license command
java -jar cdata.jdbc.airtable.jar --license
# Enter your name, email, and a license key (or TRIAL)
# 4) Configure your connection to Airtable
# Use the Connection String utility to generate a JDBC URL, then copy it for airtable.prp
java -jar cdata.jdbc.airtable.jar
# Follow the prompts, click Test Connection, then copy the connection string
# 5) Create the MCP connection file (airtable.prp)
# Use the following as a template and fill in your paths
```
Prefix=airtable
ServerName=CDataAirtable
ServerVersion=1.0
DriverPath=PATH\TO\cdata.jdbc.airtable.jar
DriverClass=cdata.jdbc.airtable.AirtableDriver
JdbcUrl=jdbc:airtable:InitiateOAuth=GETANDREFRESH;
Tables=
```
# 6) Start the MCP server (stdio) using the prp file
# This runs the server on the local machine and connects to Airtable via the JDBC driver
```
java -jar /PATH/TO/CDataMCP-jar-with-dependencies.jar /PATH/TO/airtable.prp
```
# 7) Connect via an MCP client (e.g., Claude Desktop) by registering the local stdio server
```
# Command and argument example (local stdio):
# command: java
# args: ["-jar", "/PATH/TO/CDataMCP-jar-with-dependencies.jar", "/PATH/TO/airtable.prp"]
```
> Note: The server runs in stdio mode, meaning it works with clients running on the same machine.
# 8) Test that the server is available from your client and start querying Airtable data
```bash
# Start Claude Desktop or your MCP client, then ensure the airtable MCP server is listed and connectedThe MCP server for Airtable is designed as a local, read-only bridge that exposes Airtable data as relational models via the CData JDBC Driver. It requires you to provide a JDBC connection string and a .prp file that points to the driver JAR and your Airtable connection. The server uses stdio, so you must run the client on the same machine. If you need full read, write, update, and delete capabilities, explore the other MCP server option designed for local hosting with broader permissions.
If you cannot see the MCP server in your client, ensure you have completely quit and restarted the client after adding the new server. Verify that the airtable.prp is correctly configured with your DriverPath and JdbcUrl. If you run into connection issues, re-run the JDBC Connection String utility to validate the URL and copy the exact string into airtable.prp. If problems persist, reach out to the CData Support Team for assistance.
airtable_get_tables - Retrieves a list of tables available in the data source. Output is CSV with headers.
airtable_get_columns - Retrieves a list of columns for a given table. Output is CSV with headers.
airtable_run_query - Executes a SQL SELECT query against the data source.Retrieves a list of tables available in the data source. The output is CSV with the first line containing column headers.
Retrieves a list of columns for a given table. The output is CSV with the first line containing column headers.
Executes a SQL SELECT query against the Airtable data source and returns the results.